Cross-lingual Text-to-SQL Semantic Parsing with Representation Mixup

Peng Shi, Linfeng Song, Lifeng Jin, Haitao Mi, He Bai, Jimmy Lin, Dong Yu


Abstract
We focus on the cross-lingual Text-to-SQL semantic parsing task,where the parsers are expected to generate SQL for non-English utterances based on English database schemas.Intuitively, English translation as side information is an effective way to bridge the language gap,but noise introduced by the translation system may affect parser effectiveness.In this work, we propose a Representation Mixup Framework (Rex) for effectively exploiting translations in the cross-lingual Text-to-SQL task.Particularly, it uses a general encoding layer, a transition layer, and a target-centric layer to properly guide the information flow of the English translation.Experimental results on CSpider and VSpider show that our framework can benefit from cross-lingual training and improve the effectiveness of semantic parsers, achieving state-of-the-art performance.
Anthology ID:
2022.findings-emnlp.388
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5296–5306
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.388
DOI:
10.18653/v1/2022.findings-emnlp.388
Bibkey:
Cite (ACL):
Peng Shi, Linfeng Song, Lifeng Jin, Haitao Mi, He Bai, Jimmy Lin, and Dong Yu. 2022. Cross-lingual Text-to-SQL Semantic Parsing with Representation Mixup. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 5296–5306, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Cross-lingual Text-to-SQL Semantic Parsing with Representation Mixup (Shi et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-emnlp.388.pdf